James Betker
James Betker
This is a dumb fix, but if you revert back to a commit on the master branch from a couple of months ago, you will be able to build it....
Absolutely! I have an sample NMT model which works pretty well with your library. I'll need a day or two to clean it up before submitting it, though.
Done - I've tested run_nmt on tensorflow. Not sure what backend you're using but I don't suspect there should be a problem with others as I never directly use tf.
I'm also seeing the NaNs when training the model from the code in this repo. They only appear when computing the flow chain in 'reverse' direction for me. 'Normal' is...
In case anyone runs into my problem: It appears to be just part of the training process. These artifacts do seem to reduce over time as the network trains. I...
> > In case anyone runs into my problem: It appears to be just part of the training process. These artifacts do seem to reduce over time as the network...
Yes, both that and the proportion of long sentences in the training dataset is very low.
Not sure, but if you see anything in the aforementioned cache directory or tortoise that increases in size every time the program is run, please let me know and I'll...
Don't worry about those warnings, they are innocuous. Tortoise is hit or miss for voice cloning. It doesn't work great for really unique voices.
I'm quite confident that if there is a memory leak, it is not occurring in Tortoise. I have personally run it on servers for months at a time with no...